Measuring the impact of AI on experienced open-source developer productivity

That depends on the size of the effect you’re trying to measure. If cursor provides a 5x, 10x, or 100x productivity boost as many people are claiming, you’d expect to see that in a sample size of 16 unless there’s something seriously wrong with your sample selection.

If you are looking for a 0.1% increase in productivity, then 16 is too small.

Well it depends on the variance of the random variable itself. You're right that with big, obvious effects, a larger n is less "necessary". I could see individuals having very different "productivities", especially when the idea is flattened down to completion time.

“A quarter of the participants saw increased performance, 3/4 saw reduced performance.” So I think any conclusions drawn on these 16 people doesn’t signify much one way or the other. Cool paper but how is this anything other than a null finding?

They show a 95% CI excluding zero in Figure 1. By the usual standards of social science, that's not a null finding. They give their methodology in Appendix D.

For intuition on why it's insufficient to consider N alone, I assume e.g. that you'd greatly increase your belief that a coin was unfair long before 16 consecutive heads--as already noted, the size of the effect also matters. That relationship isn't intuitive in general, and attempts to replace the math with feelings tend to fail.

Individuals do have very different productivities, but they are measuring the productivity difference across a single individual.